Automatic Driver Sleepiness Detection using Wrapper-Based Acoustic Between-Groups, Within-Groups, and Individual Feature Selection

Dara Pir, Theodore Brown, Jarek Krajewski

Abstract

This paper presents performance results, time complexities, and feature reduction aspects of three wrapper-based acoustic feature selection methods used for automatic sleepiness detection: Between-Groups Feature Selection (BGFS), Within-Groups Feature Selection (WGFS), and Individual Feature Selection (IFS) methods. Furthermore, two different methods are introduced for evaluating system performances. Our systems employ Interspeech 2011 Sleepiness Sub-Challenge’s “Sleepy Language Corpus” (SLC). The two tasks of the wrapper-based method, the feature subset evaluation and the feature space search, are performed by the Support Vector Machine classifier and a fast variant of the Best Incremental Ranked Subset algorithm, respectively. BGFS considers the feature space in Low Level Descriptor (LLD) groups, an acoustically meaningful division, allowing for significant reduction in time complexity of the computationally costly wrapper search cycles. WGFS considers the feature space within each LLD and generates the feature subset comprised of the best performing individual features among all LLDs. IFS regards the feature space individually. The best classification performance is obtained by BGFS which also achieves improvement over the Sub-Challenge baseline on the SLC test data.

References

  1. Caffier, P. P., Erdmann, U., and Ullsperger, P. (2003). Experimental evaluation of eye-blink parameters as a drowsiness measure. European Journal of Applied Physiology, 89(3-4):319-325.
  2. Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority oversampling technique. Journal of artificial intelligence research, pages 321-357.
  3. Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3):273-297.
  4. Dhupati, L. S., Kar, S., Rajaguru, A., and Routray, A. (2010). A novel drowsiness detection scheme based on speech analysis with validation using simultaneous eeg recordings. In Automation Science and Engineering (CASE), 2010 IEEE Conference on, pages 917- 921. IEEE.
  5. Eyben, F. (2016). Real-time speech and music classification by large audio feature space extraction. Springer.
  6. Eyben, F., Wöllmer, M., and Schuller, B. (2010). Opensmile: the munich versatile and fast open-source audio feature extractor. In Proceedings of the international conference on Multimedia, pages 1459-1462. ACM.
  7. Flatley, D., Reyner, L., and Horne, J. A. (2004). Sleep related crashes on sections of different road types in the UK (1995-2001). Department for Transport.
  8. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1):10-18.
  9. Hönig, F., Batliner, A., Bocklet, T., Stemmer, G., Nöth, E., Schnieder, S., and Krajewski, J. (2014a). Are men more sleepy than women or does it only look likeautomatic analysis of sleepy speech. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 995-999. IEEE.
  10. Hönig, F., Batliner, A., Nöth, E., Schnieder, S., and Krajewski, J. (2014b). Acoustic-prosodic characteristics of sleepy speech - between performance and interpretation. In Proc. of Speech Prosody, pages 864-868.
  11. Horne, J. A. and Reyner, L. A. (1995). Sleep related vehicle accidents. BMJ, 310(6979):565-567.
  12. Kohavi, R. and John, G. H. (1997). Wrappers for feature subset selection. Artificial intelligence , 97(1-2):273- 324.
  13. Krajewski, J. and Kröger, B. J. (2007). Using Prosodic and Spectral Characteristics for Sleepiness Detection. In INTERSPEECH 2007 - 8 th Annual Conference of the International Speech Communication Association, August 27-31, Antwerp, Belgium, Proceedings, pages 1841-1844.
  14. MacLean, A. W., Davies, D. R., and Thiele, K. (2003). The hazards and prevention of driving while sleepy. Sleep medicine reviews, 7(6):507-521.
  15. Maycock, G. (1996). Sleepiness and driving: the experience of uk car drivers. Journal of Sleep Research, 5(4):229-237.
  16. Ng, A. Y. (1998). On feature selection: Learning with exponentially many irrelevant features as training examples. In Proceedings of the Fifteenth International Conference on Machine Learning, ICML 7898, pages 404-412.
  17. Pir, D. and Brown, T. (2015). Acoustic Group Feature Selection Using Wrapper Method for Automatic Eating Condition Recognition. In INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association, September 6-10, 2015, Dresden, Germany, Proceedings, pages 894-898.
  18. Pir, D., Brown, T., and Krajewski, J. (2016). WrapperBased Acoustic Group Feature Selection for NoiseRobust Automatic Sleepiness Classification. In Proceedings of the 4th International Workshop on Speech Processing in Everyday Environments (CHiME 2016), September 13, 2016, San Francisco, CA, USA, pages 78-81.
  19. Ruiz, R., Riquelme, J. C., and Aguilar-Ruiz, J. S. (2006). Incremental wrapper-based gene selection from microarray data for cancer classification. Pattern Recognition, 39(12):2383-2392.
  20. Schuller, B. and Batliner, A. (2014). Computational paralinguistics: emotion, affect and personality in speech and language processing. John Wiley & Sons.
  21. Schuller, B., Steidl, S., and Batliner, A. (2009). The INTERSPEECH 2009 Emotion Challenge. In INTERSPEECH 2009 - 10 th Annual Conference of the International Speech Communication Association, September 6-10, 2009, Brighton, UK, Proceedings , pages 312-315.
  22. Schuller, B., Steidl, S., Batliner, A., Schiel, F., and Krajewski, J. (2011). The INTERSPEECH 2011 Speaker State Challenge. In INTERSPEECH 2011 - 12 th Annual Conference of the International Speech Communication Association, August 28-31, 2011, Florence, Italy, Proceedings, pages 3201-3204.
  23. Schuller, B., Steidl, S., Batliner, A., Schiel, F., Krajewski, J., Weninger, F., and Eyben, F. (2014). Medium-term speaker statesa review on intoxication, sleepiness and the first challenge. Computer Speech & Language, 28(2):346-374.
  24. Schuller, B. W., Steidl, S., Batliner, A., Hantke, S., Hönig, F., Orozco-Arroyave, J. R., Nöth, E., Zhang, Y., and Weninger, F. (2015). The INTERSPEECH 2015 Computational Paralinguistics Challenge: Nativeness, Parkinson's & Eating Condition. In INTERSPEECH 2015 - 16 th Annual Conference of the International Speech Communication Association, September 6-10, 2015, Dresden, Germany, Proceedings, pages 478- 482.
  25. Shahid, A., Wilkinson, K., Marcu, S., and Shapiro, C. M. (2012). Karolinska sleepiness scale (kss). In STOP, THAT and One Hundred Other Sleep Scales, pages 209-210. Springer.
  26. Weninger, F., Eyben, F., Schuller, B., Mortillaro, M., and Scherer, K. (2013). On the acoustics of emotion in audio: What speech, music, and sound have in common. Frontiers in psychology, 4:227-239.
Download


Paper Citation


in Harvard Style

Pir D., Brown T. and Krajewski J. (2017). Automatic Driver Sleepiness Detection using Wrapper-Based Acoustic Between-Groups, Within-Groups, and Individual Feature Selection . In Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-242-4, pages 196-202. DOI: 10.5220/0006294501960202


in Bibtex Style

@conference{vehits17,
author={Dara Pir and Theodore Brown and Jarek Krajewski},
title={Automatic Driver Sleepiness Detection using Wrapper-Based Acoustic Between-Groups, Within-Groups, and Individual Feature Selection},
booktitle={Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2017},
pages={196-202},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006294501960202},
isbn={978-989-758-242-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Automatic Driver Sleepiness Detection using Wrapper-Based Acoustic Between-Groups, Within-Groups, and Individual Feature Selection
SN - 978-989-758-242-4
AU - Pir D.
AU - Brown T.
AU - Krajewski J.
PY - 2017
SP - 196
EP - 202
DO - 10.5220/0006294501960202